Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22641
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses with the structure "as [adjective/adverb] as [noun/pronoun]."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Goods
    -0.63
    GES
    -0.60
    OUR
    -0.58
    Adds
    -0.57
    в
    -0.56
    DragonMagazine
    -0.56
    ruction
    -0.55
    470
    -0.54
    untled
    -0.54
    eor
    -0.53
    POSITIVE LOGITS
    pired
    1.07
    bestos
    1.07
     opposed
    0.98
    pires
    0.97
     regards
    0.91
     well
    0.91
    part
    0.89
    well
    0.89
    phalt
    0.89
    par
    0.89
    Activations Density 0.209%

    No Known Activations